Robot Policy Learning

Follow this topic Ask about this topic

Robot policy learning studies how robots can turn camera, depth, tactile, and proprioceptive inputs into actions for tasks such as manipulation, locomotion, and navigation. Common approaches include behavior cloning from demonstrations, reinforcement learning in simulation or on hardware, and diffusion, flow-matching, or vision-language-action policies that generate action sequences; world models and hierarchical planners can add foresight and long-horizon structure. Researchers evaluate these methods in simulation suites such as LIBERO, CALVIN, RoboTwin, and navigation benchmarks, as well as on physical robots, with growing attention to memory, contact, safety, and recovery from failure. A central tension is how to make policies generalize across tasks, robots, and changing conditions while remaining data-efficient, reactive, reliable, and fast enough to deploy.

Latest papers

377 papers85 papers in the last four weeks, up 47% on the four weeks before. 0.5% of all new papers.

Adapting Generalist Robot Policies with Semantic Reinforcement Learning
Jun 30, 2026Jagdeep Singh Bhatia, Andrew Wagenmaker, William Chen +1Robot Policy Learning Robot Policy Adaptation
U.C. Berkeley
HABIT: Human-Aware Behavior and Interaction Training Dataset for Robot Manipulation
Jun 30, 2026Jaehwi Song, Suchae Jeong, Byeongguk Jeon +4Robot Policy Learning Robotic Data Collection
Config · Config, KAIST
Multisensory Continual Learning: Adapting Pretrained Visuomotor Policies to Force
Jun 29, 2026Jaden Clark, Changhao Wang, Yihuai Gao +5Robot Policy Learning Continual Robot Learning
Stanford University
Chronos: A Physics-Informed Full-History Framework for Non-Markovian Long-Horizon Manipulation
Jun 29, 2026Yulin Zhou, Yimeng Wang, Nengyu Wang +9Robot Policy Learning Long-Horizon Robotic Manipulation
School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China
SIR: Structured Image Representations for Explainable Robot Learning
Jun 29, 2026Paul Mattes, Jan Schwab, Jens Bosch +5Robot Policy Learning Graph Representation Learning
Intuitive Robots Lab, Karlsruhe Institute of Technology, Germany · Robotics Institute Germany
Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation
Jun 29, 2026Shengqi Xu, Guojin Zhong, Yang Liu +7Robot Policy Learning Contact-Rich Robotic Manipulation
Institute of Trustworthy Embodied AI, Fudan University · Shanghai Key Laboratory of Multimodal Embodied AI · NeoteAI +1
Critical Interval MSE: Toward Reliable Offline Validation for Robot Manipulation Policies
Jun 29, 2026Haoxu Huang, Tongsam Zheng, Yifan Chen +2Robot Policy Learning Off-Policy Evaluation
Tsinghua University · Shanghai Qi Zhi Institute · Spirit AI
STEAM: Self-Supervised Temporal Ensemble Advantage Modeling for Real-World Robot Learning
Jun 29, 2026Zhihao Liu, Qiuyi Gu, Yitao Wang +16Robot Policy Learning Robot Skill Learning
Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · Zhongguancun Academy +8
Hierarchical Policy Learning via Spectral Decomposition
Jun 28, 2026Shuxin Cao, Liquan Wang, Walker Byrnes +3Robot Policy Learning Robot Skill Learning
Georgia Institute of Technology, Atlanta, Georgia, USA · Georgia Tech Research Institute, Atlanta, Georgia, USA · Harvard University, Cambridge, Massachusetts, USA
Learning Transferable Dynamics Priors from Action to World Modeling
Jun 28, 2026Ze Huang, Jiahui Zhang, Hairuo Liu +3Action-Conditioned Video Generation Robot Policy Learning
School of Data Science, Fudan University, Shanghai, China · Shanghai Innovation Institute, Shanghai, China · Shanghai Jiao Tong University, Shanghai, China +1
Behavior Uncloning: Distilling Mode Redirection into Policy Weights without Inference-Time Steering
Jun 28, 2026Hao Wang, Jiuzhou Lei, Dayou Li +5Robot Policy Learning Robot Policy Adaptation
Texas A&M University · University of Wisconsin · Northwestern University +1
Keypose Exploration: Efficient Automatic Trajectory Labelling and Cross-Embodiment Policy Transfer
Jun 27, 2026Yupu Lu, Hang Xu, Yizhou Chen +1Robot Policy Learning Cross-Embodiment Robot Learning
School of Computing and Data Science, The University of Hong Kong, HKSAR.
Scalable Behavior Cloning with Open Data, Training, and Evaluation
Jun 25, 2026Arthur Allshire, Himanshu Gaurav Singh, Ritvik Singh +15Robot Policy Learning Diffusion Transformer
UC Berkeley · MIT · XDOF +2
RouterVLA: Turning Smoke Tests into Supervision for Heterogeneous VLA Selection
Jun 25, 2026Xingyu Ren, Chugang Yi, Ge Ma +1Robot Policy Learning AI Agent Evaluation
1The Chinese University of Hong Kong · University of Maryland, College Park · 3Tsinghua University
Continual Robot Policy Learning via Variational Neural Dynamics
Jun 25, 2026Jiaxu Xing, Zhiyuan Zhu, Yunfan Ren +4Robot Policy Learning Robot Policy Adaptation
Robotics and Perception Group, University of Zurich
PhysReflect-VLA: Physical Feasibility and Self-Reflective Regulation for Reliable Vision-Language-Action Policies
Jun 25, 2026Jiayu Yang, Tao Yang, Weijun Li +4Robot Policy Learning Long-Horizon Robotic Manipulation
Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, China
RobOralScan: Learning Active Intraoral Scanning for Robotic Dental Reconstruction
Jun 25, 2026Jinhyung Lee, Haeun Yun, Siwon Kim +4RL for Robotics Robot Policy Learning
DGIST
LiMoDE: Rethinking Lifelong Robot Manipulation from a Mixture-of-Dynamic-Experts Perspective
Jun 24, 2026Zhihao Gu, Lin WangRobot Policy Learning Continual Robot Learning
School of EEE, Nanyang Technological University
Learning Asynchronous Upper-body Task-space Trajectory Tracking Policy for Humanoid Robots
Jun 24, 2026Yumeng Liu, Dongqi Wang, Jiyu Yu +3Robot Trajectory Tracking Robot Policy Learning
Zhejiang University
SAGE-Nav: Leveraging LLM Planning and Alignment Fusion for Hierarchical Scene Graph-Guided Navigation
Jun 24, 2026Hao Su, Yuehao Huang, Yukai Ma +2Robot Policy Learning Graph Neural Networks
Zhejiang University, Hangzhou, China
World Value Models for Robotic Manipulation
Jun 23, 2026Zhihao Wang, Jianxiong Li, Yu Cui +4Robot Policy Learning World Models for Robotics
ByteDance Seed · Tsinghua University · Peking University
Verifiable Foundation Models for Robot Safety
Jun 22, 2026Davide Corsi, Kyungmin Kim, Roy FoxRobot Policy Learning Robot Foundation Models
University of California, Irvine
RoboLineage: Agent-Native Data Lifecycle Governance Across Robot Policy Iterations
Jun 20, 2026Qian Luo, Wentao Guo, Zhennan Qin +4Robot Policy Learning AI Agent Governance
1Transcengram · 2The University of Hong Kong · 3Beijing Institute of Technology
Remember what you did?: Learning Behavioral Memories for Partially Observable Object Manipulation
Jun 19, 2026Kuancheng Wang, Seungho Yeom, Jinglin Cao +3Robot Policy Learning Representation Learning
UC San Diego
PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning
Jun 19, 2026Youngjoon Jeong, Jihwan Yu, Minsoo Jo +2Latent Action Learning Robot Policy Learning
Seoul National University
BayesFP: Posterior Estimation for Flow-Based Policies via Feynman-Kac Sampling
Jun 19, 2026Sreevardhan Sirigiri, Weiming Zhi, Fabio RamosDiffusion Policy Trajectory Generation
School of Computer Science, The University of Sydney, Australia · Australian Centre For Robotics, The University of Sydney, Australia · College of Connected Computing, Vanderbilt University, TN, USA. +1
When to Personalize Household Object Search: A Rigidity-Gated Hybrid Policy
Jun 18, 2026Xianyao Li, Yuhai Wang, Hu Xiao +3Robot Policy Learning Robotics
Department of Civil and Coastal Engineering, University of Florida, Gainesville, FL 32611, USA · Department of Civil and Environmental Engineering, Northeastern University, Boston, MA 02115, USA · NVIDIA
ENPIRE: Agentic Robot Policy Self-Improvement in the Real World
Jun 18, 2026Wenli Xiao, Jia Xie, Tonghe Zhang +14Robot Policy Learning Robot Skill Learning
1NVIDIA · 2CMU · 3UC Berkeley
EquiVLA: A General Framework for Rotationally Equivariant Vision-Language-Action Models
Jun 18, 2026Thien-Loc Ha, Quang-Tan Nguyen, Trong-Bao Ho +8Robot Policy Learning Diffusion Transformer
VinRobotics · VinUniversity · DFKI +2
Start Right, Arrive Right: Asynchronous Execution via Initial Noise Selection
Jun 18, 2026Trong-Bao Ho, Quang-Tan Nguyen, Thien-Loc Ha +7Robotic Control Robot Policy Learning
VinRobotics · VinUniversity · DFKI +2

Jun 30, 2026J/K move · Enter open · S save

Adapting Generalist Robot Policies with Semantic Reinforcement Learning

Jagdeep Singh Bhatia, Andrew Wagenmaker, William Chen, Sergey Levine

U.C. Berkeley

Robot Policy Learning Robot Policy Adaptation Reinforcement Learning Robot Skill Learning Robotic RL VLMs for Robotics

Open paper AskPDF arXiv

Generalist robot policies learn a diverse repertoire of behaviors from large-scale pretraining. In principle, this makes them excellent priors for downstream adaptation via reinforcement learning (RL). In practice, however, standard RL methods leveraging this prior optimize directly over robot actions, requiring the base policy's action distribution to be close to that of a performant policy from the start. This assumption breaks down for complex or long-horizon tasks that fall outside the pretraining distribution. Our key insight is that, for sufficiently expressive generalist policies, language prompts are an effective alternative space for learning to solve such tasks: modulating language inputs elicits skills already within the policy's repertoire, which can be composed to solve tasks beyond its zero-shot capabilities. We propose Semantic Action Reinforcement Learning (SARL), which learns to optimize this prompt space through online interaction, treating the generalist policy as a controllable skill prior. Importantly, leveraging pretrained skills rather than learning new ones from scratch yields structured, semantically meaningful exploration and highly efficient online improvement, and learning to modulate prompts through experience grounds them in induced real-world behaviors for robust task-solving. Across real-world settings and simulated benchmarks, we show SARL unlocks fundamentally new capabilities -- adapting VLA behavior to solve complex, long-horizon tasks -- and significantly outperforms existing approaches for improving robot behavior in deployment.